A cluster-based human resources analytics for predicting employee turnover using optimized Artificial Neural Networks and data augmentation

Decision Analytics Journal, Journal Year: 2024, Volume and Issue: 11, P. 100461 - 100461

Published: April 15, 2024

This study presents an innovative methodology to predict employee turnover by integrating Artificial Neural Networks (ANN) with clustering techniques. We focus on hyperparameter tuning various input parameters obtain optimal ANN models. By segmenting data, the identifies critical predictors, allowing targeted interventions be implemented improve efficiency and effectiveness of retention policies. Data augmentation using Conditional Generative Adversarial (CTGAN) is performed clusters imbalanced data. Following this, optimized models are applied these augmented clusters, leading a notable improvement in their performance. evaluate our against five other variants four traditional machine learning demonstrate superior accuracy recall. The proposed approach achieves operational advantages shifting away from generalized strategies more focused, cluster-based policies, which can optimize resource utilization reduce costs. Because its practicality enhanced ability manage turnover, this method, supported empirical evidence, significant advancement human (HR) analytics

Language: Английский

---

Unrealistic Optimism Regarding Artificial Intelligence Opportunities in Human Resource Management

International Journal of Knowledge Management, Journal Year: 2023, Volume and Issue: 19(1), P. 1 - 19

Published: Jan. 27, 2023

Artificial intelligence (AI) has many uses in domains like automotive and finance or business divisions human resource management (HRM). This study presents a survey that was conducted among German national sample (n = 79) of HRM personnel from small- medium-sized enterprises regarding the expected impact AI on their own other companies. Indications for unrealistic optimism, i.e., assuming negative impacts are more likely others than oneself, were identified. will play an increasingly important role, with cost reductions efficiency gains serving as highest motives lack specialists representing inhibitor. Participants assume reduce number employees companies, while it let one grow. They expect to take over tasks companies believe companies' HRM, especially administrative processing. Future research should include (repeated) investigations into divisions.

Language: Английский

---

A Deep Learning Model Based on Bidirectional Temporal Convolutional Network (Bi-TCN) for Predicting Employee Attrition

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(6), P. 2984 - 2984

Published: March 10, 2025

Employee attrition, which causes a significant loss for an organization, is the term used to describe natural decline in number of employees organization as result numerous unavoidable events. If company can predict likelihood employee leaving, it take proactive steps address issue. In this study, we introduce deep learning framework based on Bidirectional Temporal Convolutional Network (Bi-TCN) attrition. We conduct extensive experiments two publicly available datasets, including IBM and Kaggle, comparing our model’s performance against classical machine learning, models, state-of-the-art approaches across multiple evaluation metrics. The proposed model yields promising results predicting achieving accuracy rates 89.65% dataset 97.83% Kaggle dataset. also apply fully connected GAN-based data augmentation technique three oversampling methods augment balance show that model, combined with approach, improves 92.17%. applied SHAP method identify key features most significantly influence These findings demonstrate efficacy showcasing its potential use various industries organizations.

Language: Английский

---

Analysis and classification of employee attrition and absenteeism in industry: A sequential pattern mining-based methodology

Computers in Industry, Journal Year: 2024, Volume and Issue: 159-160, P. 104106 - 104106

Published: May 27, 2024

Language: Английский

---

Predicting Nurse Turnover for Highly Imbalanced Data Using SMOTE and Machine Learning Algorithms

Published: Nov. 1, 2023

Predicting nurse turnover is a growing challenge within the healthcare sector, profoundly impacting quality and nursing profession. This study employs Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance issues in 2018 National Sample Survey of Registered Nurses (NSSRN) dataset predict using machine learning (ML) algorithms. Four ML algorithms, namely logistic regression (LR), random forests (RF), decision tree (DT), extreme gradient boosting (XGBoost), are applied SMOTE-enhanced dataset. The data randomly split into an 80% training set 20% validation set. Eighteen carefully selected variables from NSSRN database serve as predictive features, model identifies feature importance concerning turnover. includes performance comparison based on metrics such Accuracy, Precision, Recall (Sensitivity), F1-score, AUC. In summary, results demonstrate that (SMOTE_RT) exhibit most robust power, both classical approach (with all 18 variables) optimized (utilizing eight key variables). XGBoost, tree, follow performance. Notably, age emerges influential factor turnover, with working hours, EHR/EMR usability, individual income, region also playing significant roles. research offers valuable insights for researchers stakeholders, aiding selecting suitable algorithms prediction.

Language: Английский

---

Accelerated ADAM Optimizer with Warm-Up using Multilayer Perceptron (MLP) to Predict Employee Turnover

Published: June 21, 2024

Language: Английский

---

Explainable Machine Learning and Graph Neural Network Approaches for Predicting Employee Attrition

Published: Aug. 8, 2024

Language: Английский

---

Predicting Nurse Turnover for Highly Imbalanced Data Using the Synthetic Minority Over-Sampling Technique and Machine Learning Algorithms

Healthcare, Journal Year: 2023, Volume and Issue: 11(24), P. 3173 - 3173

Published: Dec. 15, 2023

Predicting nurse turnover is a growing challenge within the healthcare sector, profoundly impacting quality and nursing profession. This study employs Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance issues in 2018 National Sample Survey of Registered Nurses dataset predict using machine learning algorithms. Four algorithms, namely logistic regression, random forests, decision tree, extreme gradient boosting, were applied SMOTE-enhanced dataset. The data split into 80% training 20% validation sets. Eighteen carefully selected variables from database served as predictive features, model identified age, working hours, electric health record/electronic medical record, individual income, job type important features concerning turnover. includes performance comparison based on accuracy, precision, recall (sensitivity), F1-score, AUC. In summary, results demonstrate that forests exhibit most robust power classical approach (with all 18 variables) an optimized (utilizing eight key variables). Extreme regression follow performance. Notably, age emerges influential factor turnover, with record usability, region also playing significant roles. research offers valuable insights for researchers stakeholders, aiding selecting suitable algorithms prediction.

Language: Английский

---

Enhancing Book Recommendations on GoodReads: A Data Mining Approach Based Random Forest Classification

Lecture notes in networks and systems, Journal Year: 2024, Volume and Issue: unknown, P. 395 - 409

Published: Jan. 1, 2024

Language: Английский

---

A Systematic Literature Review of Quantitative Models for Predicting Employee Attrition

2022 International Conference on Decision Aid Sciences and Applications (DASA), Journal Year: 2024, Volume and Issue: unknown, P. 1 - 7

Published: Dec. 11, 2024

Language: Английский

---